set_global
AI agents use set_global to create or update resources in Iris Execute — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Iris Execute environment.
The 'set_global' tool modifies IRIS global variables, which are persistent data stores. This is a Write operation (reversible modification) rather than Read (get_global exists as separate tool) or Destructive (does not delete data).
From the tool's definition Tool named 'set_global' on an InterSystems IRIS execution server alongside tools for ObjectScript execution and compilation. The name 'set_global' indicates modification of global variables in IRIS, which are persistent data structures.
Attacks that exploit this kind of access
set_global. It is categorised as a Write tool in the Iris Execute MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Iris Execute MCP server in PolicyLayer and add a rule for set_global: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Iris Execute. Nothing to install.
set_global is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the set_global rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for set_global. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
set_global is provided by the Iris Execute MCP server (jbrandtmse/iris-execute-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
set_global is one line of Iris Execute's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →